*SEM 2019

The Eighth Joint Conference on Lexical and Computational Semantics

June 6-7, 2019, Minneapolis, USA

Co-located with NAACL 2019

Welcome!

We are pleased to announce that SIGLEX and SIGSEM, special interest groups of the ACL, are organizing the 8th Joint Conference on Lexical and Computational Semantics: *SEM. *SEM 2019 will be co-located with NAACL-HLT 2019 in Minneapolis (USA), and it will take place on the 6-7 of June 2019. We will update this website with more information as it becomes available.

Latest news

April 09, 2019 If you need a visa invitation letter, please fill the form here. Visit this link to find more information on the US visa application process.

March 05, 2019 The long and short paper submission deadline has been extended. New deadline: March 10, 2019. See Important Dates section on the home page.

December 29, 2018. The deadlines for long & short paper submissions, notification of acceptance, and camera ready versions are now posted. See Important Dates section on the home page.



Programme

Thursday, June 6th, 2019
09:00 - 10:30    Session 1 (Chair: Ekaterina Shutova)
09:15 - 09:30    Opening remarks
09:30 - 10:30    Invited Talk by Sam Bowman (New York University): “Task-Independent Sentence Understanding”
10:30 - 11:00    Coffee break
11:00 - 12:30    Session 2: Lexical Semantics (Chair: Saif M. Mohammad)
11:00 - 11:30    SURel: A Gold Standard for Incorporating Meaning Shifts into Term Extraction 
Anna Hätty1, Dominik Schlechtweg2, Sabine Schulte im Walde2
1Robert Bosch GmbH, 2University of Stuttgart
11:30 - 12:00    Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes 
Aina Garí Soler1, Marianna Apidianaki2, Alexandre Allauzen3
1LIMSI, CNRS, Université Paris-Sud, 2CNRS, 3Université Paris-Sud / LIMSI-CNRS
12:00 - 12:30    Beyond Context: A New Perspective for Word Embeddings 
Yichu Zhou and Vivek Srikumar
University of Utah
12:30 - 14:00    Lunch break
14:00 - 15:30    Session 3: Sentence Representations (Chair: Barry Devereux)
14:00 - 14:30    Composition of Embeddings : Lessons from Statistical Relational Learning 
Damien Sileo1, Tim Van de Cruys2, Camille Pradel3, Philippe Muller4
1IRIT, Synapse Développement, 2IRIT & CNRS, 3Synapse Développement, 4IRIT, Toulouse University
14:30 - 15:00    Multi-Label Transfer Learning for Multi-Relational Semantic Similarity 
Li Zhang, Steven Wilson, Rada Mihalcea
University of Michigan
15:00 - 15:30    Scalable Cross-Lingual Transfer of Neural Sentence Embeddings 
Hanan Aldarmaki1 and Mona Diab2
1The George Washington University, 2GWU
15:30 - 16:00    Coffee break
16:00 - 18:00    Poster session
16:00 - 16:50    Poster booster (Chair: Marianna Apidianaki)
16:50 - 18:00    Poster session
Second-order contexts from lexical substitutes for few-shot learning of word representations 
Qianchu Liu1, Diana McCarthy2, Anna Korhonen1
1University of Cambridge, 2University of Cambridge (DTAL)
Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis 
Dongfang Xu, Egoitz Laparra, Steven Bethard
University of Arizona
Bot2Vec: Learning Representations of Chatbots 
Jonathan Herzig1, Tommy Sandbank2, Michal Shmueli-Scheuer1, David Konopnicki3
1IBM Research, 2Similari LTD, 3IBM
Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors 
Anne Lauscher and Goran Glavaš
University of Mannheim
A Semantic Cover Approach for Topic Modeling 
Rajagopal Venkatesaramani1, Doug Downey2, Bradley Malin3, Yevgeniy Vorobeychik1
1Washington University in St. Louis, 2Northwestern University, Allen AI, 3Vanderbilt University
MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants 
Simon Ostermann1, Michael Roth2, Manfred Pinkal1
1Saarland University, 2University of Stuttgart
Deconstructing multimodality: visual properties and visual context in human semantic processing 
Christopher Davis1, Luana Bulat1, Anita Lilla Verő1, Ekaterina Shutova2
1University of Cambridge, 2University of Amsterdam
Learning Graph Embeddings from WordNet-based Similarity Measures 
Andrey Kutuzov1, Mohammad Dorgham2, Oleksiy Oliynyk2, Alexander Panchenko2, Chris Biemann2
1University of Oslo, 2University of Hamburg
Neural User Factor Adaptation for Text Classification: Learning to Generalize Across Author Demographics 
Xiaolei Huang1 and Michael J. Paul2
1Dept. of Information Science, University of Colorado Boulder, 2University of Colorado
Abstract Graphs and Abstract Paths for Knowledge Graph Completion 
Vivi Nastase1 and Bhushan Kotnis2
1University of Heidelberg, 2NEC Laboaratories Europe
A Corpus of Negations and their Underlying Positive Interpretations 
Zahra Sarabi, Erin Killian, Eduardo Blanco, Alexis Palmer
University of North Texas
Enthymemetic Conditionals 
Eimear Maguire
Université Paris Diderot / Laboratoire de Linguistique Formelle
Acquiring Structured Temporal Representation via Crowdsourcing: A Feasibility Study 
Yuchen Zhang and Nianwen Xue
Brandeis University
Exploration of Noise Strategies in Semi-supervised Named Entity Classification 
Pooja Lakshmi Narayan1, Ajay Nagesh2, Mihai Surdeanu1
1University of Arizona, 2DiDi AI Labs
Improving Generalization in Coreference Resolution via Adversarial Training 
Sanjay Subramanian1 and Dan Roth2
1University of Pennsylvania, 2University of Pennsylvania; University of Illinois Urbana-Champaign
Improving Human Needs Categorization of Events with Semantic Classification 
Haibo Ding1, Ellen Riloff2, Zhe Feng1
1Bosch Research and Technology Center, 2University of Utah
Friday, June 7th, 2019
09:00 - 10:30    Session 1 (Chair: Lun-Wei Ku)
09:00 - 10:00    Invited talk by Ellen Riloff (University of Utah): “Identifying Affective Events and the Reasons for their Polarity”
10:00 - 10:30    Word Embeddings (Also) Encode Human Personality Stereotypes 
Oshin Agarwal1, Funda Durupınar2, Norman I. Badler1, Ani Nenkova1
1University of Pennsylvania, 2Bilkent University
10:30 - 11:00    Coffee break
11:00 - 12:30    Session 2: Semantics and Syntax (Chair: Kilian Evang)
11:00 - 11:30    Automatic Accuracy Prediction for AMR Parsing 
Juri Opitz1 and Anette Frank2
1Heidelberg University, 2Heidelberg Universiy
11:30 - 12:00    An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling 
Juri Opitz1 and Anette Frank2
1Heidelberg University, 2Heidelberg Universiy
12:00 - 12:30    Probing What Different NLP Tasks Teach Machines about Function Word Comprehension 
Najoung Kim1, Roma Patel2, Adam Poliak1, Patrick Xia1, Alex Wang3, Tom McCoy1, Ian Tenney4, Alexis Ross5, Tal Linzen1, Benjamin Van Durme6, Samuel R. Bowman3, Ellie Pavlick2
1Johns Hopkins University, 2Brown University, 3New York University, 4Google, 5Harvard University, 6JHU
12:30 - 14:00    Lunch break
14:00 - 15:30    Session 3: Inference (Chair: Ellen Riloff)
14:00 - 14:30    HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning 
Hitomi Yanaka1, Koji Mineshima2, Daisuke Bekki2, Kentaro Inui3, Satoshi Sekine4, Lasha Abzianidze5, Johan Bos5
1RIKEN AIP, 2Ochanomizu University, 3Tohoku University / RIKEN AIP, 4Riken, AIP, 5CLCG, University of Groningen
14:30 - 15:00    On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference 
Yonatan Belinkov1, Adam Poliak2, Stuart Shieber3, Benjamin Van Durme4, Alexander Rush5
1MIT CSAIL, 2Johns Hopkins University, 34JHU, 5Harvard University
15:00 - 15:30    Bayesian Inference Semantics: A Modelling System and A Test Suite 
Jean-Philippe Bernardy1, Rasmus Blanck1, Stergios Chatzikyriakidis1, Shalom Lappin2, Aleksandre Maskharashvili3
1University of Gothenburg, 2King's College London, 3Gothenburg University
15:30 - 16:00    Coffee break
16:00 - 17:30    Session 4: Applications (Chair: Steve Wilson)
16:00 - 16:30    Target Based Speech Act Classification in Political Campaign Text 
Shivashankar Subramanian1, Trevor Cohn1, Timothy Baldwin2
1University of Melbourne, 2The University of Melbourne
16:30 - 17:00    Incivility Detection in Online Comments 
Farig Sadeque1, Stephen Rains1, Yotam Shmargad1, Kate Kenski1, Kevin Coe2, Steven Bethard1
1University of Arizona, 2University of Utah
17:00 - 17:30    Generating Animations from Screenplays 
Yeyao Zhang1, Eleftheria Tsipidi2, Sasha Schriber3, Mubbasir Kapadia4, Markus Gross1, Ashutosh Modi3
1ETH Zurich, 2Disney Research Zurich, 3Disney Research, 4Rutgers University

Keynote Speakers

The following speakers have accepted to give keynotes at *SEM 2019.

Speaker: Ellen Riloff

Date: TBC

Title: Identifying Affective Events and the Reasons for their Polarity

Abstract: Recognizing affective states is essential for narrative text understanding and for applications such as conversational dialogue, summarization, and sarcasm recognition. Many tools have been developed to recognize explicit expressions of sentiment, but affective states can also be inferred from events. This talk will focus on "affective events", which are generally desirable or undesirable experiences that implicitly suggest an affective state for the experiencer. For example, buying a home is usually desirable and associated with a positive affective state, but being laid off is undesirable and associated with a negative state. First, we will describe a weakly supervised learning method to induce affective events from a text corpus by optimizing for semantic consistency. Second, we aim to characterize affective events based on Human Needs Categories, which often explain people's motivations, goals, and desires. We will present a co-training model for Human Needs categorization that uses an event expression classifier and an event context classifier to learn from both labeled and unlabeled texts.

Bio: Ellen Riloff is a Professor in the School of Computing at the University of Utah. Her primary research area is natural language processing, with an emphasis on information extraction, affective text analysis, semantic class induction, and bootstrapping methods that learn from unannotated texts. Prof. Riloff has served as the General Chair for the EMNLP 2018 conference, Program Co-Chair for the NAACL HLT 2012 and CoNLL 2004 conferences, on the NAACL Executive Board for 2004-2005 and 2017-2018, the Computational Linguistics Editorial Board, and the Transactions of the Association for Computational Linguistics (TACL) Editorial Board. In 2018, Prof. Riloff was named a Fellow of the Association for Computational Linguistics (ACL).

Speaker: Sam Bowman

Date: TBC

Title: Task-Independent Sentence Understanding

Abstract: This talk deals with the goal of task-independent language understanding: building machine learning models that can learn to do most of the hard work of language understanding before they see a single example of the language understanding task they're meant to solve, in service of making the best of modern NLP systems both better and more data-efficient. I'll survey the (dramatic!) progress that the NLP research community has made toward this goal in the last year. In particular, I'll dwell on GLUE—an open-ended shared task competition that measures progress toward this goal for sentence understanding tasks—and I'll preview a few recent and forthcoming analysis papers that attempt to offer a bit of perspective on this recent progress.

Bio: I have been on the faculty at NYU since 2016, when I finished my PhD with Chris Manning and Chris Potts at Stanford. At NYU, I'm a core member of the new school-level Data Science unit, which focuses on machine learning, and a co-PI of the CILVR machine learning lab. My research focuses on data, evaluation techniques, and modeling techniques for sentence understanding in natural language processing, and on applications of machine learning to scientific questions in linguistic syntax and semantics. I am an area chair for *SEM 2018, ICLR 2019, and NAACL 2019; I organized a twenty-three person team at JSALT 2018; and I earned a 2015 EMNLP Best Resource Paper Award and a 2017 Google Faculty Research Award.

Call for papers

*SEM 2019 brings together researchers interested in the semantics of natural languages and its computational modeling. The conference embraces symbolic and probabilistic approaches, and everything in between; theoretical contributions as well as practical applications are welcome. The long-term goal of *SEM is to provide a stable forum for the growing number of NLP researchers working on all aspects of semantics. Topics of interest include, but are not limited to:


  • Lexical semantics and word representations
  • Compositional semantics and sentence representations
  • Statistical, machine learning and deep learning methods in semantic tasks
  • Multilingual and cross-lingual semantics
  • Word sense disambiguation and induction
  • Semantic parsing; syntax-semantics interface
  • Frame semantics and semantic role labeling
  • Textual inference, entailment and question answering
  • Formal approaches to semantics
  • Extraction of events and causal and temporal relations
  • Entity linking; pronouns and coreference
  • Discourse, pragmatics and dialogue
  • Machine reading
  • Extra-propositional aspects of meaning
  • Multiword and idiomatic expressions
  • Metaphor, irony, and humour
  • Knowledge mining and acquisition
  • Common sense reasoning
  • Language generation
  • Semantics in NLP applications: sentiment analysis, abusive language detection, summarization, fact checking, etc.
  • Multidisciplinary research on semantics
  • Grounding and multimodal semantics
  • Human semantic processing
  • Semantic annotation, evaluation and resources
  • Ethical aspects and bias in semantic representations


Important Dates

Paper submission deadline: March 10, 2019
Notification of acceptance: April 3, 2019
Camera-ready papers due: April 10, 2019
Timezone: as long as it’s the date mentioned, anywhere on earth; UTC-12.



Submission Instructions

Submissions to *SEM 2019 must describe unpublished work and be written in English. We solicit both long and short papers.

Long papers describe original research and may consist of up to eight (8) pages of content, plus unlimited pages for references. Final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers' comments can be taken into account.

Short papers describe original focused research, project or system description, and may consist of up to four (4) pages, plus unlimited pages for references. Upon acceptance, short papers will be given five (5) content pages in the proceedings. Authors are encouraged to use this additional page to address reviewers comments in their final versions.

As the reviewing will be blind, the paper must not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity, e.g., "We previously showed (Smith, 1991) ..." must be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ...". As for online paper sharing, at *SEM, we adopt the ACL policy for submission, which can be found here. Papers that do not conform to requirements will be rejected without review. For a paper to be included in the conference proceedings, at least one of the authors must be registered as a participant at the *SEM conference.

Submissions to *SEM should follow this year's NAACL style, as detailed here: https://naacl2019.org/calls/papers/

Please note that double submission of papers will need to be notified at submission.

Key dates

Paper submission deadline: March 10, 2019
Notification of acceptance: April 3, 2019
Camera-ready papers due: April 10, 2019
*SEM conference: June 6-7, 2019

Timezone: as long as it’s the date mentioned, anywhere on earth; UTC-12.

Organizing Committee

General Chair: Rada Mihalcea, University of Michigan, Ann Arbor
Program Chairs:

Ekaterina Shutova, University of Amsterdam

Lun-Wei Ku, Academia Sinica, Taiwan

Publications Chair: Kilian Evang, University of Düsseldorf
Publicity Chair: Soujanya Poria, NTU, Singapore

Area Chairs

Lexical semantics and word representations:

Anna Feldman, Montclair State University

Fabio Massimo Zanzotto, University of Rome Tor Vergata

Semantic composition and sentence representations:

Helen Yannakoudakis, University of Cambridge

Douwe Kiela, Facebook AI Research

Discourse, dialogue and generation :

Lea Frermann, Amazon Core AI

Lu Wang, Northeastern University

Machine learning for semantic tasks:

Roi Reichart, Technion - Israel Institute of Technology

Wilker Aziz, University of Amsterdam

Multidisciplinary & COI: Preslav Nakov, QCRI
Multilinguality: Marianna Apidianaki, CNRS
Human semantic processing / Psycholinguistics: Barry Devereux, Queen’s University Belfast
Semantics in NLP applications:

Dan Goldwasser, Purdue University

Saif Mohammad, National Research Council of Canada

Marek Rei, University of Cambridge

Resources and evaluation: Beata Beigman Klebanov, Educational Testing Service
Theoretical and formal semantics: Mehrnoosh Sadrzadeh, Queen Mary University of London